Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/jansenanalytics/claudex/contextgit clone --depth 1 https://github.com/JansenAnalytics/claudexWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00019 | $0.00333 |
| Opus 5 | $0.00010 | $0.00167 |
| Sonnet 5 | $0.00004 | $0.00067 |
| Haiku 4.5 | $0.00002 | $0.00033 |
Grade A, and why
context scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Produce a structured context dump so the user (or another session) can pick up where this one left off.
Pull from these sources, in this order:
- Today's daily memory —
~/.claude-agent/memory/YYYY-MM-DD.mdif it exists. Summarize, don't paste. - Yesterday's daily memory — same, for continuity.
- Active tasks —
TaskListoutput, grouped by status. Highlight in-progress tasks. - Inbox —
node ~/.claude-agent/scripts/inbox.cjs --listif there are pending entries. - Recent plans — list any files in
~/.claude-agent/memory/plans/modified in the last 7 days with their titles. - Recent decisions/learnings —
node --experimental-sqlite ~/.claude-agent/scripts/memory-search.cjs --search "decision OR learned OR figured out" --limit 5 --source memory --quietif the index is built. - Cross-agent flags — anything from Kite/Poe/Argus daily files in the last 24h that mentions Claudex.
Output format: Telegram-friendly message. Use bold headers per section, bullets within. Skip empty sections silently. Cap at ~30 lines — the goal is a usable handoff, not an exhaustive transcript.
End with a "Resume point:" line — one sentence saying what the next session should do first.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 21 lines · 19 tokens per session scan A 8492928da8b6
context is a command published in the GitHub repository JansenAnalytics/claudex (5 stars, last pushed 2mo ago), licensed MIT. It adds 19 tokens to every session and 333 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.